This paper introduces the extended description of a database that contains emotional speech in the Russian language of younger school age (8–12-year-old) children and describes the results of validation of the database based on classical machine learning algorithms, such as Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP). The validation is performed using standard procedures and scenarios of the validation similar to other well-known databases of children’s emotional acting speech. Performance evaluation of automatic multiclass recognition on four emotion classes “Neutral (Calm)—Joy—Sadness—Anger” shows the superiority of SVM performance and also MLP performance over the results of perceptual tests. Moreover, the results of automatic recognition on the test dataset which was used in the perceptual test are even better. These results prove that emotions in the database can be reliably recognized both by experts and automatically using classical machine learning algorithms such as SVM and MLP, which can be used as baselines for comparing emotion recognition systems based on more sophisticated modern machine learning methods and deep neural networks. The results also confirm that this database can be a valuable resource for researchers studying affective reactions in speech communication during child-computer interactions in the Russian language and can be used to develop various edutainment, health care, etc. applications.

We investigate a neural network–based solution for the Automatic Meter Reading detection problem, applied to analog dial gauges. We employ a convolutional neural network with a non-linear Network in Network kernel. Presently, there is a significant interest in systems for automatic detection of analog dial gauges, particularly in the energy and household sectors, but the problem is not yet sufficiently addressed in research. Our method is a universal three-level model that takes an image as an input and outputs circular bounding areas, object classes, grids of reference points for all symbols on the front panel of the device and positions of display pointers. Since all analog pointer meters have a common nature, this multi-cascade model can serve various types of devices if its capacity is sufficient. The model is using global regression for locations of symbols, which provides resilient results even for low image quality and overlapping symbols. In this work, we do not focus on the pointer location detection since it heavily depends on the shape of the pointer. We prepare training data and benchmark the algorithm with our own framework a3net, not relying on third-party neural network solutions. The experimental results demonstrate the versatility of the proposed methods, high accuracy, and resilience of reference points detection.

A Virtual Dialogue Assistant (VDA) is an automated system intended to provide support for conducting tests and examinations in the context of distant education platforms. Online Distance Learning (ODL) has proven to be a critical part of education systems across the world, particularly during the COVID-19 pandemic. While the core components of ODL are sufficiently researched and developed to become mainstream, there is still a demand for various aspects of traditional classroom learning to be implemented or improved to match the expectations for modern ODL systems. In this work, we take a look at the evaluation of students’ performance. Various forms of testing are often present in ODL systems; however, modern Natural Language Processing (NLP) techniques provide new opportunities to improve this aspect of ODL. In this paper, we present an overview of VDA intended for integration with online education platforms to enhance the process of evaluation of students’ performance. We propose an architecture of such a system, review challenges and solutions for building it, and present examples of solutions for several NLP problems and ways to integrate them into the system. The principal challenge for ODL is accessibility; therefore, proposing an enhancement for ODL systems, we formulate the problem from the point of view of a user interacting with it. In conclusion, we affirm that relying on the advancements in NLP and Machine Learning, the approach we suggest can provide an enhanced experience of evaluation of students’ performance for modern ODL platforms.

In this paper, we present a continuation of our work on the personification of dialogue agents. We expand upon the previously demonstrated models—the ranking and generative models—and propose new hybrid models. Because there is no single definitive way to build a hybrid model, we explore various architectures where the components adopt different roles, sequentially and in parallel. Applying the perplexity and BLEU performance metrics, we discover that the Retrieve and Refine and KG model—a modification of the Retrieve and Refine model where the ranking and generative components work in parallel and compete based on the proximity of the candidate found by the ranking model with a knowledge-grounded generation block—achieves the best performance, with values of 1.64 for perplexity and 0.231 for BLEU scores.